Neuro-Adaptive Backstepping Controller Design for High-Speed Trains

Abstract

Unrestrained lateral and roll motion can result in a risk in the operational safety of high-speed trains (HSTs) system. This paper explores the backstepping control technique to curb these motions. The HST is a higher order multiple-input-multiple-output (MIMO) system consists of nonlinear coupled dynamics. The general uncertainties along with nonlinearities presented in the dynamics of the system are approximated with radial basis function neural network (RBFNN). Stability analysis of the proposed method is carried out using Lyapunov theory. Trajectory tracking simulations of HST system are carried out to validate the efficacy and usefulness of the proposed method which ensures that the tracking errors asymptotically converge to zero.